mlsanityData to 14 Oct 2026

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models

arXiv 2407.13796 ↗First posted 16 Jul 2024cs.CR cs.AI cs.CLcited by 2

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak vulnerabilities arising from continuous embeddings has been limited, as prior approaches primarily involved appending discrete or continuous suffixes to inputs. Our study presents a novel channel for conducting direct attacks on LLM inputs, eliminating the need for suffix addition or specific questions provided that the desired output is predefined. We additionally observe that extensive iterations often lead to overfitting, characterized by repetition in the output. To counteract this, we propose a simple yet effective strategy named CLIP. Our experiments show that for an input length of 40 at iteration 1000, applying CLIP improves the ASR from 62% to 83%

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 18 of its 23 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

18 of 23 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space14 Feb
  2. 2024Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning13 Feb
  3. 2023Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking16 Nov
  4. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks16 Oct
  5. 2023Multilingual Jailbreak Challenges in Large Language Models10 Oct
  6. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  7. 2023Low-Resource Languages Jailbreak GPT-43 Oct
  8. 2023Certifying LLM Safety against Adversarial Prompting6 Sep
  9. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  10. 2023MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots16 Jul
  11. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 7

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  5. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  6. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  7. 2023Adversarial Attacks and Defenses in Large Language Models: Old and New Threatscited by 49

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
  2. 2026Adaptive Prompt Embedding Optimization for LLM Jailbreakingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
  2. 2025CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
  3. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
  4. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey
  5. 2024A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
  6. 2024Improved Large Language Model Jailbreak Detection via Pretrained Embeddings
  7. 2026ShallowJail: Steering Jailbreaks against Large Language Models
  8. 2024Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models